feature(zzh): add STEVE algorithm

[ZHZisZZ]

Description

add STEVESACPolicy in ding/policy/mbpolicy/mbsac.py

Related Issue

TODO

Check List

• merge the latest version source branch/repo, and resolve all the conflicts
• pass style check
• pass all the tests

[codecov]

Codecov Report

Merging #363 (014d189) into main (47940ef) will decrease coverage by 0.17%.
The diff coverage is 95.57%.

@@            Coverage Diff             @@
##             main     #363      +/-   ##
==========================================
- Coverage   85.87%   85.70%   -0.18%     
==========================================
  Files         522      526       +4     
  Lines       40835    41193     +358     
==========================================
+ Hits        35069    35306     +237     
- Misses       5766     5887     +121     

Flag	Coverage Δ
unittests	85.70% <95.57%> (-0.18%)	⬇️

Flags with carried forward coverage won't be shown. Click here to find out more.

Impacted Files	Coverage Δ
ding/world_model/ddppo.py	76.01% <77.77%> (+0.07%)	⬆️
ding/torch_utils/reshape_helper.py	83.33% <83.33%> (ø)
ding/world_model/mbpo.py	81.53% <92.30%> (+1.53%)	⬆️
ding/policy/mbpolicy/mbsac.py	96.00% <96.80%> (+0.49%)	⬆️
ding/entry/tests/test_serial_entry_mbrl.py	80.95% <100.00%> (+4.48%)	⬆️
ding/policy/command_mode_policy_instance.py	95.09% <100.00%> (+0.07%)	⬆️
ding/policy/mbpolicy/tests/test_mbpolicy_utils.py	100.00% <100.00%> (ø)
ding/policy/mbpolicy/utils.py	100.00% <100.00%> (+15.78%)	⬆️
ding/torch_utils/__init__.py	100.00% <100.00%> (ø)
ding/torch_utils/tests/test_reshape_helper.py	100.00% <100.00%> (ø)
... and 27 more

---

Continue to review full report at Codecov.

Legend - Click here to learn more
Δ = absolute <relative> (impact), ø = not affected, ? = missing data
Powered by Codecov. Last update 47940ef...014d189. Read the comment docs.